episode_read

Default model descriptor

{
  "name": "episode_read",
  "title": "Read an episode",
  "description": "Reads an EPISODE (comp_...) as stitched transcript prose with inline navigation hints, visual evidence, segment manifest, speaker legend (per-speaker word share/talk_seconds — \"who spoke how much\" is answerable here), and duration/revision. The Program map reports each source-backed occurrence's current caption treatment and each Junction's current Cut, Crossfade, or Produced transition treatment, with a Crossfade's look and, per Junction, the looks the selected renderer draws there (looks; empty where a crossfade can't join). The Camera Program reports exact Episode-local explicit picture decisions—including source-linked synchronized versus continuous picture time—plus access-scoped inherited/automatic intervals the renderer currently selects, so `none` means no local override rather than necessarily base footage. The Picture Program reports bounded exact simultaneous-layout reauthoring segments and Episode-scoped evidence; its continuation also carries `picture_read_token`. Typed opener/outro occurrences include safe current `identity_customization` state. Each footage occurrence and placed photo says it can host picture layers (layer_host) and lists its layers compactly: id, window in its own seconds, the recording_id and kind (photo or video) shown, and placement (full, or box with its frame fractions). A parent Episode read also returns bounded derived-Clip titles and exact reopen handles, so a named existing Clip is found through its likely parent; docs and speaker tools do not list Clip titles. For Project content-evidence asks, transcript_search returns the windows this read takes as `window`. Also ACCEPTS a recording handle (src_...) and reads it as that recording's episode-of-one. All timestamps are EPISODE time unless a field ends in _source. Long transcripts are PAGINATED, in sequence via `page`. Every continuation (page or picture_page after 1) requires the `expected_revision` and `expected_program_digest` its hint prints (plus `picture_read_token` when the hint carries one); a missing or changed pin refuses, and the read restarts at page 1. The pins hold one Program revision and digest (and Picture read token), not the transcript: a retranscription between pages can pass them and show as changed words, and page 1 reflects the current transcript. Transcript words and times are approximate read-only semantic locators; a structural boundary requires source media evidence from a narrow episode_zoom or exact episode_sample_frames projection:\"original\" samples. Program and angle previews never authorize structural boundaries. This read opens nothing: opening is workspace_open, and saved reviewable Moments are review_points_place with exact Episode-time ranges and the revision returned here. A timestamp named in chat is neither an open nor a saved review point. Returns prose only, never word-level rows. Does not modify anything.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "episode_id": {
        "type": "string",
        "description": "The episode public ID, such as comp_...; a recording src_... handle is also accepted for a recording's episode-of-one."
      },
      "composition_id": {
        "type": "string",
        "description": "Backward-compatible alias for episode_id."
      },
      "window": {
        "type": "object",
        "description": "Optional EPISODE-time span to read for long episodes. Lines overlapping the window are returned; absent means the whole episode.",
        "properties": {
          "from": {
            "type": "number",
            "description": "Window start in episode seconds; absent means an open start."
          },
          "to": {
            "type": "number",
            "description": "Window end in episode seconds; absent means an open end."
          }
        }
      },
      "page": {
        "type": "integer",
        "description": "1-indexed page of the transcript prose (default 1). A long transcript is split into M pages so each stays under the host's tool-output size cap; the returned page's header says 'page N of M' and its footer says how to fetch the next. Composes with `window`: `window` picks the time range, `page` paginates that range's prose."
      },
      "picture_page": {
        "type": "integer",
        "minimum": 1,
        "description": "Independent 1-indexed page of bounded Picture Scene and Picture Evidence summaries. Continuations are the exact ones returned in Picture Program prose."
      },
      "expected_revision": {
        "type": "integer",
        "minimum": 0,
        "description": "Required on every continuation (page or picture_page after 1): the revision the previous page's continuation hint prints. A changed Episode refuses and the read restarts at page 1."
      },
      "expected_program_digest": {
        "type": "string",
        "pattern": "^[0-9a-f]{64}$",
        "description": "Required with expected_revision on every continuation: the Program digest the previous page's continuation hint prints. It also moves on a same-revision occurrence change such as align_span; a changed Program refuses and the read restarts at page 1."
      },
      "picture_read_token": {
        "type": "string",
        "pattern": "^[0-9a-f]{64}$",
        "description": "Required exact media-generation pin returned by Picture Program page 1 when following a Picture or transcript continuation that carries Picture content."
      }
    },
    "required": [],
    "additionalProperties": false,
    "anyOf": [
      {
        "required": [
          "episode_id"
        ]
      },
      {
        "required": [
          "composition_id"
        ]
      }
    ]
  },
  "annotations": {
    "title": "Read an episode",
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ]
  }
}

App descriptor

{
  "name": "episode_read",
  "title": "Read an episode",
  "description": "Reads an EPISODE (comp_...) as stitched transcript prose with inline navigation hints, visual evidence, segment manifest, speaker legend (per-speaker word share/talk_seconds — \"who spoke how much\" is answerable here), and duration/revision. The Program map reports each source-backed occurrence's current caption treatment and each Junction's current Cut, Crossfade, or Produced transition treatment, with a Crossfade's look and, per Junction, the looks the selected renderer draws there (looks; empty where a crossfade can't join). The Camera Program reports exact Episode-local explicit picture decisions—including source-linked synchronized versus continuous picture time—plus access-scoped inherited/automatic intervals the renderer currently selects, so `none` means no local override rather than necessarily base footage. The Picture Program reports bounded exact simultaneous-layout reauthoring segments and Episode-scoped evidence; its continuation also carries `picture_read_token`. Typed opener/outro occurrences include safe current `identity_customization` state. Each footage occurrence and placed photo says it can host picture layers (layer_host) and lists its layers compactly: id, window in its own seconds, the recording_id and kind (photo or video) shown, and placement (full, or box with its frame fractions). A parent Episode read also returns bounded derived-Clip titles and exact reopen handles, so a named existing Clip is found through its likely parent; docs and speaker tools do not list Clip titles. For Project content-evidence asks, transcript_search returns the windows this read takes as `window`. Also ACCEPTS a recording handle (src_...) and reads it as that recording's episode-of-one. All timestamps are EPISODE time unless a field ends in _source. Long transcripts are PAGINATED, in sequence via `page`. Every continuation (page or picture_page after 1) requires the `expected_revision` and `expected_program_digest` its hint prints (plus `picture_read_token` when the hint carries one); a missing or changed pin refuses, and the read restarts at page 1. The pins hold one Program revision and digest (and Picture read token), not the transcript: a retranscription between pages can pass them and show as changed words, and page 1 reflects the current transcript. Transcript words and times are approximate read-only semantic locators; a structural boundary requires source media evidence from a narrow episode_zoom or exact episode_sample_frames projection:\"original\" samples. Program and angle previews never authorize structural boundaries. This read opens nothing: opening is workspace_open, and saved reviewable Moments are review_points_place with exact Episode-time ranges and the revision returned here. A timestamp named in chat is neither an open nor a saved review point. Returns prose only, never word-level rows. Does not modify anything.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "episode_id": {
        "type": "string",
        "description": "The episode public ID, such as comp_...; a recording src_... handle is also accepted for a recording's episode-of-one."
      },
      "composition_id": {
        "type": "string",
        "description": "Backward-compatible alias for episode_id."
      },
      "window": {
        "type": "object",
        "description": "Optional EPISODE-time span to read for long episodes. Lines overlapping the window are returned; absent means the whole episode.",
        "properties": {
          "from": {
            "type": "number",
            "description": "Window start in episode seconds; absent means an open start."
          },
          "to": {
            "type": "number",
            "description": "Window end in episode seconds; absent means an open end."
          }
        }
      },
      "page": {
        "type": "integer",
        "description": "1-indexed page of the transcript prose (default 1). A long transcript is split into M pages so each stays under the host's tool-output size cap; the returned page's header says 'page N of M' and its footer says how to fetch the next. Composes with `window`: `window` picks the time range, `page` paginates that range's prose."
      },
      "picture_page": {
        "type": "integer",
        "minimum": 1,
        "description": "Independent 1-indexed page of bounded Picture Scene and Picture Evidence summaries. Continuations are the exact ones returned in Picture Program prose."
      },
      "expected_revision": {
        "type": "integer",
        "minimum": 0,
        "description": "Required on every continuation (page or picture_page after 1): the revision the previous page's continuation hint prints. A changed Episode refuses and the read restarts at page 1."
      },
      "expected_program_digest": {
        "type": "string",
        "pattern": "^[0-9a-f]{64}$",
        "description": "Required with expected_revision on every continuation: the Program digest the previous page's continuation hint prints. It also moves on a same-revision occurrence change such as align_span; a changed Program refuses and the read restarts at page 1."
      },
      "picture_read_token": {
        "type": "string",
        "pattern": "^[0-9a-f]{64}$",
        "description": "Required exact media-generation pin returned by Picture Program page 1 when following a Picture or transcript continuation that carries Picture content."
      }
    },
    "required": [],
    "additionalProperties": false,
    "anyOf": [
      {
        "required": [
          "episode_id"
        ]
      },
      {
        "required": [
          "composition_id"
        ]
      }
    ]
  },
  "annotations": {
    "title": "Read an episode",
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ]
  }
}

Live Workspace descriptor

{
  "name": "episode_read",
  "title": "Read an episode",
  "description": "Reads an EPISODE (comp_...) as stitched transcript prose with inline navigation hints, visual evidence, segment manifest, speaker legend (per-speaker word share/talk_seconds — \"who spoke how much\" is answerable here), and duration/revision. The Program map reports each source-backed occurrence's current caption treatment and each Junction's current Cut, Crossfade, or Produced transition treatment, with a Crossfade's look and, per Junction, the looks the selected renderer draws there (looks; empty where a crossfade can't join). The Camera Program reports exact Episode-local explicit picture decisions—including source-linked synchronized versus continuous picture time—plus access-scoped inherited/automatic intervals the renderer currently selects, so `none` means no local override rather than necessarily base footage. The Picture Program reports bounded exact simultaneous-layout reauthoring segments and Episode-scoped evidence; its continuation also carries `picture_read_token`. Typed opener/outro occurrences include safe current `identity_customization` state. Each footage occurrence and placed photo says it can host picture layers (layer_host) and lists its layers compactly: id, window in its own seconds, the recording_id and kind (photo or video) shown, and placement (full, or box with its frame fractions). A parent Episode read also returns bounded derived-Clip titles and exact reopen handles, so a named existing Clip is found through its likely parent; docs and speaker tools do not list Clip titles. For Project content-evidence asks, transcript_search returns the windows this read takes as `window`. Also ACCEPTS a recording handle (src_...) and reads it as that recording's episode-of-one. All timestamps are EPISODE time unless a field ends in _source. Long transcripts are PAGINATED, in sequence via `page`. Every continuation (page or picture_page after 1) requires the `expected_revision` and `expected_program_digest` its hint prints (plus `picture_read_token` when the hint carries one); a missing or changed pin refuses, and the read restarts at page 1. The pins hold one Program revision and digest (and Picture read token), not the transcript: a retranscription between pages can pass them and show as changed words, and page 1 reflects the current transcript. Transcript words and times are approximate read-only semantic locators; a structural boundary requires source media evidence from a narrow episode_zoom or exact episode_sample_frames projection:\"original\" samples. Program and angle previews never authorize structural boundaries. This read opens nothing: opening is workspace_get_link, and saved reviewable Moments are review_points_place with exact Episode-time ranges and the revision returned here. A timestamp named in chat is neither an open nor a saved review point. Returns prose only, never word-level rows. Does not modify anything.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "episode_id": {
        "type": "string",
        "description": "The episode public ID, such as comp_...; a recording src_... handle is also accepted for a recording's episode-of-one."
      },
      "composition_id": {
        "type": "string",
        "description": "Backward-compatible alias for episode_id."
      },
      "window": {
        "type": "object",
        "description": "Optional EPISODE-time span to read for long episodes. Lines overlapping the window are returned; absent means the whole episode.",
        "properties": {
          "from": {
            "type": "number",
            "description": "Window start in episode seconds; absent means an open start."
          },
          "to": {
            "type": "number",
            "description": "Window end in episode seconds; absent means an open end."
          }
        }
      },
      "page": {
        "type": "integer",
        "description": "1-indexed page of the transcript prose (default 1). A long transcript is split into M pages so each stays under the host's tool-output size cap; the returned page's header says 'page N of M' and its footer says how to fetch the next. Composes with `window`: `window` picks the time range, `page` paginates that range's prose."
      },
      "picture_page": {
        "type": "integer",
        "minimum": 1,
        "description": "Independent 1-indexed page of bounded Picture Scene and Picture Evidence summaries. Continuations are the exact ones returned in Picture Program prose."
      },
      "expected_revision": {
        "type": "integer",
        "minimum": 0,
        "description": "Required on every continuation (page or picture_page after 1): the revision the previous page's continuation hint prints. A changed Episode refuses and the read restarts at page 1."
      },
      "expected_program_digest": {
        "type": "string",
        "pattern": "^[0-9a-f]{64}$",
        "description": "Required with expected_revision on every continuation: the Program digest the previous page's continuation hint prints. It also moves on a same-revision occurrence change such as align_span; a changed Program refuses and the read restarts at page 1."
      },
      "picture_read_token": {
        "type": "string",
        "pattern": "^[0-9a-f]{64}$",
        "description": "Required exact media-generation pin returned by Picture Program page 1 when following a Picture or transcript continuation that carries Picture content."
      }
    },
    "required": [],
    "additionalProperties": false,
    "anyOf": [
      {
        "required": [
          "episode_id"
        ]
      },
      {
        "required": [
          "composition_id"
        ]
      }
    ]
  },
  "annotations": {
    "title": "Read an episode",
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ]
  }
}

Errors

[
  "composition_not_found",
  "stale_composition_revision",
  "stale_program_digest",
  "stale_picture_read",
  "invalid_input"
]

Examples

[
  {
    "label": "See a whole episode before clipping it",
    "input": {
      "episode_id": "comp_..."
    }
  }
]